Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Varied document snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ្�
    -0.08
     phái
    -0.06
    чили
    -0.06
     आग
    -0.06
     western
    -0.06
     वर
    -0.06
    (parameters
    -0.06
     complete
    -0.06
     آرام
    -0.06
    警察
    -0.06
    POSITIVE LOGITS
     rotor
    0.07
     Mick
    0.06
     mover
    0.06
     LJ
    0.06
     передбач
    0.06
     Rich
    0.06
     Hy
    0.06
    Dub
    0.06
    ZR
    0.06
     Slot
    0.06
    Act Density 0.000%

    No Known Activations